Esta dissertação busca investigar processos de escrita audiovisual em que a trilha sonora é um elemento narrativo e dramático construído a partir do roteiro. A pesquisa teórica baseia-se na análise de manuais de roteiro e em guias sobre som no audiovisual. O objetivo desta análise é encontrar as circunstâncias em que a trilha sonora é considerada elemento integrante do processo de escrita de obras audiovisuais. Nossa principal questão é se existem regras e padrões para uma produção de textos que estabeleçam a função do som desde o processo criativo inicial da composição de uma obra audiovisual, considerando a dialética som-imagem. A pesquisa empírica tem como base a leitura analítica de roteiros de filmagem de diferentes autores, visando entender como se descreve ou enuncia a banda sonora em cada um deles. Considerando que roteiros não são a obra final, os escritos analisados são comparados com os filmes já prontos. Nosso objetivo é, por meio desta pesquisa, colaborar para o instrumental teórico e prático a que um roteirista pode recorrer no momento de desenvolvimento de um relato cinematográfico ou audiovisual. / The aim of this research is to investigate screenwriting processes in which the soundtrack is a narrative and dramatic element built from the script. The theoretical research is based on an analysis of script manuals and guides about sound in the audiovisual media. The objective of this analysis is to find the circumstances in which the soundtrack is considered an integral element of the writing process of audiovisual works. Our main question is whether there are rules and standards for the production of texts that establish the function of the sound from the initial creative process of composition of an audiovisual work, considering the dialectics sound-image. Empirical research is based on the analytical reading of scripts by different authors, in order to understand how each of them describes or announces the soundtrack. Whereas scripts are not the final work, scripts are compared with the films. Our goal is, through this research, to contribute to the theoretical and practical resources that a writer can refer to when developing a cinematographic or audiovisual story.

Esta dissertação busca investigar processos de escrita audiovisual em que a trilha sonora é um elemento narrativo e dramático construído a partir do roteiro. A pesquisa teórica baseia-se na análise de manuais de roteiro e em guias sobre som no audiovisual. O objetivo desta análise é encontrar as circunstâncias em que a trilha sonora é considerada elemento integrante do processo de escrita de obras audiovisuais. Nossa principal questão é se existem regras e padrões para uma produção de textos que estabeleçam a função do som desde o processo criativo inicial da composição de uma obra audiovisual, considerando a dialética som-imagem. A pesquisa empírica tem como base a leitura analítica de roteiros de filmagem de diferentes autores, visando entender como se descreve ou enuncia a banda sonora em cada um deles. Considerando que roteiros não são a obra final, os escritos analisados são comparados com os filmes já prontos. Nosso objetivo é, por meio desta pesquisa, colaborar para o instrumental teórico e prático a que um roteirista pode recorrer no momento de desenvolvimento de um relato cinematográfico ou audiovisual. / The aim of this research is to investigate screenwriting processes in which the soundtrack is a narrative and dramatic element built from the script. The theoretical research is based on an analysis of script manuals and guides about sound in the audiovisual media. The objective of this analysis is to find the circumstances in which the soundtrack is considered an integral element of the writing process of audiovisual works. Our main question is whether there are rules and standards for the production of texts that establish the function of the sound from the initial creative process of composition of an audiovisual work, considering the dialectics sound-image. Empirical research is based on the analytical reading of scripts by different authors, in order to understand how each of them describes or announces the soundtrack. Whereas scripts are not the final work, scripts are compared with the films. Our goal is, through this research, to contribute to the theoretical and practical resources that a writer can refer to when developing a cinematographic or audiovisual story.

Generating computer animation from natural language instructions is a complex task that encompasses several key aspects of artificial intelligence including natural language understanding, computer graphics and knowledge representation. Traditionally, this task has been approached using rule based systems which were highly successful on their respective domains, but were difficult to generalise to other domains. In this thesis, I describe the key theories and principles behind a domain-independent machine learning framework for constructing natural language based animation systems, and show how this framework can be more flexible and more powerful than the prevalent rule based approach. / I begin this thesis with a thorough introduction to the goals of the research. I then review the most relevant literature to put this research into perspective. After the literature review, I provide brief descriptions to the most relevant technologies in both natural language processing and computer graphics. I then report original research in semantic role labelling and verb sense disambiguation, followed by a detailed description and analysis of the machine learning framework for natural language based animation generation. / The key contributions of this thesis are: a novel method for performing semantic role labelling of prepositional phrases, a novel method for performing verb sense disambiguation, and a novel machine learning framework for grounding linguistic information in virtual worlds and converting verb-semantic information to computer graphics commands to create computer animation.

No description available.